{"id":"https://openalex.org/W4416756238","doi":"https://doi.org/10.1109/access.2025.3637156","title":"A Frustum-Aware Fusion Network With Cross-Attention for Multi-Modal 3D Detection","display_name":"A Frustum-Aware Fusion Network With Cross-Attention for Multi-Modal 3D Detection","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416756238","doi":"https://doi.org/10.1109/access.2025.3637156"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3637156","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3637156","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3637156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101783984","display_name":"Jingkun Xu","orcid":"https://orcid.org/0000-0002-0720-8045"},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkun Xu","raw_affiliation_strings":["School of Computer and Information Science, Chongqing Normal University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information Science, Chongqing Normal University, Chongqing, China","institution_ids":["https://openalex.org/I126924076"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038622074","display_name":"Ke Xiao","orcid":"https://orcid.org/0000-0002-1858-832X"},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Xiao","raw_affiliation_strings":["School of Computer and Information Science, Chongqing Normal University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-1858-832X","affiliations":[{"raw_affiliation_string":"School of Computer and Information Science, Chongqing Normal University, Chongqing, China","institution_ids":["https://openalex.org/I126924076"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041516314","display_name":"Wenjie Ji","orcid":"https://orcid.org/0009-0009-7730-0080"},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Ji","raw_affiliation_strings":["School of Computer and Information Science, Chongqing Normal University, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0009-7730-0080","affiliations":[{"raw_affiliation_string":"School of Computer and Information Science, Chongqing Normal University, Chongqing, China","institution_ids":["https://openalex.org/I126924076"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chunlin Li","orcid":"https://orcid.org/0009-0002-8604-1278"},"institutions":[{"id":"https://openalex.org/I126924076","display_name":"Chongqing Normal University","ror":"https://ror.org/01dcw5w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I126924076"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlin Li","raw_affiliation_strings":["School of Computer and Information Science, Chongqing Normal University, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0002-8604-1278","affiliations":[{"raw_affiliation_string":"School of Computer and Information Science, Chongqing Normal University, Chongqing, China","institution_ids":["https://openalex.org/I126924076"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32817976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"200777","last_page":"200790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9129999876022339,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9129999876022339,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.022199999541044235,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.020999999716877937,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.8206999897956848},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.600600004196167},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5372999906539917},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5230000019073486},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.47870001196861267},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4731999933719635},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.44510000944137573},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4422000050544739},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4212999939918518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259999752044678},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.8206999897956848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6312000155448914},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.600600004196167},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5532000064849854},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5372999906539917},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5230000019073486},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4212999939918518},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.3901999890804291},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3458999991416931},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.33820000290870667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.273499995470047},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C141297171","wikidata":"https://www.wikidata.org/wiki/Q1143237","display_name":"Octree","level":2,"score":0.2651999890804291}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3637156","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3637156","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:31e74e98cc1d4c36975dfc4b7b99a46d","is_oa":true,"landing_page_url":"https://doaj.org/article/31e74e98cc1d4c36975dfc4b7b99a46d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 200777-200790 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3637156","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3637156","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5558427748","display_name":null,"funder_award_id":"CSTB2023NSCQ-LZX0139","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G6635426339","display_name":null,"funder_award_id":"YKC24009","funder_id":"https://openalex.org/F4320329228","funder_display_name":"Science Research Foundation of Xijing University"},{"id":"https://openalex.org/G8236701352","display_name":null,"funder_award_id":"2024NSCQ-MSX3125","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"}],"funders":[{"id":"https://openalex.org/F4320323172","display_name":"Natural Science Foundation of Chongqing","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329228","display_name":"Science Research Foundation of Xijing University","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"achievement":[1],"of":[2,11,38,77,139,163,169,187,201,226,244],"precise":[3],"3D":[4,81,164,199],"object":[5,82,252],"detection":[6,153],"via":[7],"LiDAR\u2013camera":[8],"fusion":[9,54,79,168],"is":[10,120,148],"utmost":[12],"importance":[13],"for":[14,80,206,230],"enabling":[15],"autonomous":[16],"driving":[17],"in":[18],"complex":[19],"traffic":[20],"environments.":[21],"However,":[22],"existing":[23],"methods":[24],"encounter":[25],"two":[26],"substantial":[27],"challenges:":[28],"spatial":[29],"misalignment":[30],"among":[31],"heterogeneous":[32],"sensor":[33],"modalities":[34],"and":[35,69,130,161,181,204,213,228,232,247],"the":[36,75,137,159,178,185,188,192,207,218,221],"loss":[37],"fine-grained":[39],"geometric":[40,103],"details":[41],"during":[42],"cross-modal":[43,97],"feature":[44,98],"fusion.":[45],"To":[46],"address":[47],"these":[48],"issues,":[49],"we":[50,85],"propose":[51],"a":[52,61,116,143],"frustum-aware":[53],"network":[55,59],"with":[56,108],"cross-attention.":[57],"This":[58],"utilizes":[60,151],"unified":[62],"point\u2013voxel":[63,171],"representation":[64,138],"to":[65,122,157],"integrate":[66],"both":[67],"image":[68],"point":[70,106,125],"cloud":[71],"data,":[72],"thus":[73],"improving":[74],"quality":[76],"multi-modal":[78,89],"detection.":[83],"Specifically,":[84],"present":[86],"an":[87],"innovative":[88],"alignment":[90,99],"module":[91,146],"(MAM)":[92],"that":[93],"achieves":[94,198,242],"more":[95],"accurate":[96],"by":[100],"integrating":[101],"depth-aware":[102],"structures":[104],"from":[105,113],"clouds":[107,126],"high-level":[109],"semantic":[110],"features":[111],"extracted":[112],"images.":[114],"Subsequently,":[115],"sliding":[117],"frustum":[118],"mechanism":[119],"employed":[121],"dynamically":[123],"partition":[124],"within":[127],"target":[128],"regions":[129],"extract":[131],"their":[132],"key":[133],"features,":[134,165],"thereby":[135],"refining":[136],"local":[140],"geometry.":[141],"Moreover,":[142,236],"region-aligned":[144],"attention":[145],"(RAAM)":[147],"designed,":[149],"which":[150],"2D":[152],"boxes":[154],"as":[155],"queries":[156],"guide":[158],"refinement":[160],"focus":[162],"facilitating":[166],"adaptive":[167],"multi-scale":[170],"representations.":[172],"Finally,":[173],"extensive":[174],"experiments":[175],"conducted":[176],"on":[177,237],"KITTI,":[179],"NuScenes,":[180],"Waymo":[182],"datasets":[183],"validate":[184],"effectiveness":[186],"proposed":[189,222],"framework.":[190],"On":[191,217],"KITTI":[193],"test":[194],"set,":[195],"our":[196,240],"method":[197],"mAPs":[200],"90.88%,":[202],"84.47%,":[203],"80.99%":[205],"Car":[208],"category":[209],"under":[210],"Easy,":[211],"Moderate,":[212],"Hard":[214],"settings,":[215],"respectively.":[216,235],"NuScenes":[219],"benchmark,":[220],"model":[223],"attains":[224],"APs":[225],"89.2%":[227],"64.9%":[229],"Pedestrian":[231],"Bicycle":[233],"detection,":[234],"theWaymo":[238],"dataset,":[239],"framework":[241],"3DmAPHscores":[243],"82.07%":[245],"(L1)":[246],"76.38%":[248],"(L2)":[249],"across":[250],"all":[251],"categories,":[253],"demonstrating":[254],"significant":[255],"improvements":[256],"over":[257],"current":[258],"state-of-the-art":[259],"approaches.":[260]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-25T00:00:00"}